AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Fairness-Aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models

CVPR 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Attacks and defenses in sequential settings · 53 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add FAAP input perturbationsNormal training ResNet-18 · CelebA SmilingDEO: 0.0774 -> 0.0327Helped
Add FAAP input perturbationsNormal training ResNet-18 · CelebA AttractiveDEO: 0.5683 -> 0.0621Helped
Add FAAP input perturbationsNormal training ResNet-18 · CelebA Blond_HairDEO: 0.5299 -> 0.1013Helped
Add FAAP input perturbationsNormal training ResNet-18 · LFW SmilingDEO: 0.1472 -> 0.0534Helped
Add FAAP perturbations generated using surrogate modelsCommercial face analysis APIs · Alibaba APIDEO: 0.0952 -> 0.0368Helped
Add FAAP perturbations generated using surrogate modelsCommercial face analysis APIs · Baidu APIDEO: 0.1035 -> 0.0387Helped
Add FAAP input perturbationsNormal training ResNet-18 · CelebA AttractiveACC: 82.43% -> 79.73%Hurt
Add FAAP perturbations generated using surrogate modelsCommercial face analysis APIs · Baidu APIACC: 90.47% -> 87.58%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy